Correlations between Word Vector Sets

Vitalii Zhelezniak, April Shen, Daniel Busbridge, Aleksandar Savkov, Nils Hammerla


Abstract
Similarity measures based purely on word embeddings are comfortably competing with much more sophisticated deep learning and expert-engineered systems on unsupervised semantic textual similarity (STS) tasks. In contrast to commonly used geometric approaches, we treat a single word embedding as e.g. 300 observations from a scalar random variable. Using this paradigm, we first illustrate that similarities derived from elementary pooling operations and classic correlation coefficients yield excellent results on standard STS benchmarks, outperforming many recently proposed methods while being much faster and trivial to implement. Next, we demonstrate how to avoid pooling operations altogether and compare sets of word embeddings directly via correlation operators between reproducing kernel Hilbert spaces. Just like cosine similarity is used to compare individual word vectors, we introduce a novel application of the centered kernel alignment (CKA) as a natural generalisation of squared cosine similarity for sets of word vectors. Likewise, CKA is very easy to implement and enjoys very strong empirical results.
Anthology ID:
D19-1008
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
77–87
Language:
URL:
https://aclanthology.org/D19-1008
DOI:
10.18653/v1/D19-1008
Bibkey:
Cite (ACL):
Vitalii Zhelezniak, April Shen, Daniel Busbridge, Aleksandar Savkov, and Nils Hammerla. 2019. Correlations between Word Vector Sets. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 77–87, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Correlations between Word Vector Sets (Zhelezniak et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-bitext-workshop/D19-1008.pdf
Attachment:
 D19-1008.Attachment.zip
Code
 Babylonpartners/corrsim